{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_1a122761cd5556633fd8bcd47317844b63d9120fa9a44bca6989629d6f387a2e","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_1a122761cd5556633fd8bcd47317844b63d9120fa9a44bca6989629d6f387a2e","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"1e1f6480e30e978213f6e9ea9609b945ab79d3ce7319e15e0f043c95f87ef177","published":"Fri, 03 Jul 2026 00:00:00 -0400","receipt_hash":"1e1f6480e30e978213f6e9ea9609b945ab79d3ce7319e15e0f043c95f87ef177","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"1e1f6480e30e978213f6e9ea9609b945ab79d3ce7319e15e0f043c95f87ef177","observed_at":"2026-07-03T04:43:38.241623Z","parent_run_hash":"f0e30469786257a5e74170498cacb4c028623bf32d6d06d4dbadc488960545be","published":"Fri, 03 Jul 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2607.02504v1 Announce Type: cross \nAbstract: Long-form TV dramas present a formidable challenge for comprehensive video understanding, where deciphering complex storyline often relies on \\textbf{speaker recognition}, the task of accurately attributing each spoken utterance to its respective character. In this paper, we advance this field through two primary contributions. (1) We introduce \\textbf{DramaSR-532K}, a large-scale benchmark comprising 532K annotated dialogue lines across more than 900 unique characters, necessitating the integration of auditory, linguistic, and visual cues for speaker recognition. (2) We propose \\textbf{DramaSR-LRM}, a robust approach built upon a large reasoning model (LRM). DramaSR-LRM is designed to autonomously aggregate contextual evidence via multimodal tool-use, synthesizing diverse inputs to achieve high-fidelity attribution. Experimental results demonstrate that DramaSR-LRM significantly outperforms existing baselines, particularly on short ut","title":"Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas","url":"https://arxiv.org/abs/2607.02504","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.02504v1 Announce Type: cross \nAbstract: Long-form TV dramas present a formidable challenge for comprehensive video understanding, where deciphering complex storyline often relies on \\textbf{speaker recognition}, the task of accurately attributing each spoken utterance to its respective character. In this paper, we advance this field through two primary contributions. (1) We introduce \\textbf{DramaSR-532K}, a large-scale benchmark comprising 532K annotated dialogue lines across more than 900 unique characters, necessitating the integration of auditory, linguistic, and visual cues for speaker recognition. (2) We propose \\textbf{DramaSR-LRM}, a robust approach built upon a large reasoning model (LRM). DramaSR-LRM is designed to autonomously aggregate contextual evidence via multimodal tool-use, synthesizing diverse inputs to achieve high-fidelity attribution. Experimental results demonstrate that DramaSR-LRM significantly outperforms existing baselines, particularly on short ut","title":"Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-03T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.02504"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:e396b7eeb0458d47d163b86c302effcdc4302f0f1ecefaa3767897eed6cd73976339131f28de9be80c8aee5ae40e6193d09c34ba4465872956b9774a25670205","signer":"crovia.substrate","subject":{"observed_at":"2026-07-03T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.02504"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"4c4b1860d268c23930bcc57d5fa5940517687389a446e530a4f58d50470528fb","leaf_index":275560,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"1e0169c1151c06aac444cd2e34fb6607636059c0e89d35566130aee9edf423cf","side":"right"},{"sibling":"43671e85d080ad5ba1ae1bfd4b055b97140133d3244d53d63771b1f5897a0a7b","side":"right"},{"sibling":"840ccc9f419c41dcde2106720a98914f0d4002d5e8c86def098c8cec6c24479f","side":"right"},{"sibling":"da0b2596a9cc150c84c44903a6890ea2713f6ee97f41f15b296a3e0dd7606893","side":"left"},{"sibling":"aa327fd26209e8ed7821ef98250d5f32ca511fec73e2131c80edaafd929ab722","side":"right"},{"sibling":"2b5e2a5410e7530377c7735b21156dbbfffce39d4e6f9a311d7de5ea760a0f5f","side":"left"},{"sibling":"951a1a1b501b86a4c8935e5f14dcd40ccd2d9f000d8c1cc584a81c95ee1b3755","side":"left"},{"sibling":"5e5c8e8db37d5481fef0ead807ae94ad0195c7ae0cf92622f52c3dec100a7e16","side":"right"},{"sibling":"da9343635b180d3ddf07636b2a7814fcbf809adc1979958fa092ef6d16ef0db5","side":"right"},{"sibling":"1685b068d9bba0447845c97429c2a9ba728526abe2dc9d9522fed7b13d6620e4","side":"right"},{"sibling":"cf1e47b22a12b71fda307cbe1b98bc247fa4226ac8691ca8d99e6cc72a905b34","side":"left"},{"sibling":"4dbd8247ba08a5432c7d6540711da9acb2f59e6189865aa8552dee37f69286a9","side":"right"},{"sibling":"41cd1885dc3fcb51e49eeb887d6d22ec2cfa58df0e4f8d7c7dddf3a1b0ce8249","side":"left"},{"sibling":"8a09562f6b247c1c3cd1fea36cb3b8f1cf5c575479dd514573856a380a964bf5","side":"left"},{"sibling":"723981908169653ca6d835aa9b8381a8c7ad3e3e3830d0792bc32032cda615ee","side":"right"},{"sibling":"c0594fa1ee81d5f019cccc7b5e51af603c6d7e43995498c451012060c7d06165","side":"right"},{"sibling":"4de6a2fb22efbb50c84dc62abeb0f2cbc8c663a9540aeba9e758ebfdfe3e86dd","side":"right"},{"sibling":"fdbb3519f8dc411a4043dfb5abdbfea5441e130326183ac2247c42584033f152","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":275799,"merkle_root":"2581d0d6e5fa345cdf2e8ab3b191ace76d6b14189901ab0e4c2291ca1d1ae1e6","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260703T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-03T05:38:09Z","sig_algorithm":"ed25519","signature":"e44a386a5ae00c0e7fc67b1179bb9060bf0fefc006e454fec70e27668182ff497d1e2faf0c3b22de0917beefb7c80e880dae925a3f67e1b16aa0eb44bf947407","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_1a122761cd5556633fd8bcd47317844b63d9120fa9a44bca6989629d6f387a2e"}}